{"id":"https://openalex.org/W3037110041","doi":"https://doi.org/10.1109/tpds.2020.3004623","title":"GPGPU Performance Estimation With Core and Memory Frequency Scaling","display_name":"GPGPU Performance Estimation With Core and Memory Frequency Scaling","publication_year":2020,"publication_date":"2020-06-24","ids":{"openalex":"https://openalex.org/W3037110041","doi":"https://doi.org/10.1109/tpds.2020.3004623","mag":"3037110041"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.3004623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3004623","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018867983","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-2986-967X"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018867983"],"corresponding_institution_ids":["https://openalex.org/I141568987"],"apc_list":null,"apc_paid":null,"fwci":7.7768,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.98052773,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":"12","first_page":"2865","last_page":"2881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/frequency-scaling","display_name":"Frequency scaling","score":0.9230515956878662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582607507705688},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7781808376312256},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7007870078086853},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.664960503578186},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5874051451683044},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5324175357818604},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.47817426919937134},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.47453773021698},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.45308318734169006},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.45028242468833923},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.440743088722229},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42822781205177307},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3860335648059845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3448626399040222},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10479813814163208}],"concepts":[{"id":"https://openalex.org/C157742956","wikidata":"https://www.wikidata.org/wiki/Q3237776","display_name":"Frequency scaling","level":3,"score":0.9230515956878662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582607507705688},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7781808376312256},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7007870078086853},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.664960503578186},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5874051451683044},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5324175357818604},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.47817426919937134},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.47453773021698},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.45308318734169006},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.45028242468833923},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.440743088722229},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42822781205177307},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3860335648059845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3448626399040222},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10479813814163208},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2020.3004623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3004623","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W192356505","https://openalex.org/W1495021188","https://openalex.org/W1555915743","https://openalex.org/W1904624772","https://openalex.org/W1978969737","https://openalex.org/W1980489165","https://openalex.org/W2009343317","https://openalex.org/W2019998101","https://openalex.org/W2038666141","https://openalex.org/W2060076314","https://openalex.org/W2074084090","https://openalex.org/W2080592089","https://openalex.org/W2086724906","https://openalex.org/W2092340922","https://openalex.org/W2099019585","https://openalex.org/W2109426995","https://openalex.org/W2110195531","https://openalex.org/W2149234156","https://openalex.org/W2155893237","https://openalex.org/W2163687928","https://openalex.org/W2167334577","https://openalex.org/W2170059648","https://openalex.org/W2233640613","https://openalex.org/W2493312715","https://openalex.org/W2497599918","https://openalex.org/W2522820499","https://openalex.org/W2529165666","https://openalex.org/W2559876875","https://openalex.org/W2583218561","https://openalex.org/W2586392553","https://openalex.org/W2614112306","https://openalex.org/W2725179571","https://openalex.org/W2760837370","https://openalex.org/W2761434131","https://openalex.org/W2762077810","https://openalex.org/W2786865931","https://openalex.org/W2787719654","https://openalex.org/W2790957308","https://openalex.org/W2794513473","https://openalex.org/W2796649226","https://openalex.org/W2901073342","https://openalex.org/W2921788688","https://openalex.org/W2930604630","https://openalex.org/W2943912161","https://openalex.org/W2944280939","https://openalex.org/W2945148926","https://openalex.org/W2962843187","https://openalex.org/W2963926583","https://openalex.org/W3152476980","https://openalex.org/W6723386527","https://openalex.org/W6733214920","https://openalex.org/W6750448596"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2153506571"],"abstract_inverted_index":{"Contemporary":[0],"graphics":[1],"processing":[2],"units":[3],"(GPUs)":[4],"support":[5],"dynamic":[6],"voltage":[7],"and":[8,15,20,71,94,104,133,143],"frequency":[9,31,46,73,131],"scaling":[10,127],"to":[11,42,60,76,84,97],"balance":[12],"computational":[13],"performance":[14,22,106,120,126],"energy":[16,49],"consumption.":[17],"However,":[18],"accurate":[19],"straightforward":[21],"estimation":[23],"for":[24,36,48],"a":[25,56,99,147],"given":[26],"GPU":[27,66,151],"kernel":[28,105,125],"under":[29,129],"different":[30,130],"settings":[32,132],"is":[33,40],"still":[34],"lacking":[35],"real":[37,87],"hardware,":[38,88],"which":[39,80],"essential":[41],"determine":[43],"the":[44,62,77,118,124],"best":[45],"configuration":[47],"saving.":[50],"In":[51],"this":[52],"article,":[53],"we":[54],"reveal":[55],"fine-grained":[57],"analytical":[58],"model":[59,90,121],"estimate":[61],"execution":[63],"time":[64],"of":[65,101,139,149],"kernels":[67,152],"with":[68,153],"both":[69],"core":[70],"memory":[72],"scaling.":[74],"Compared":[75],"cycle-level":[78],"simulators,":[79],"are":[81],"too":[82],"slow":[83],"apply":[85],"on":[86,146],"our":[89],"only":[91],"needs":[92],"simple":[93],"one-off":[95],"micro-benchmarks":[96],"extract":[98],"set":[100,148],"hardware":[102],"parameters":[103],"counters":[107],"without":[108],"any":[109],"source":[110],"code":[111],"analysis.":[112],"Our":[113],"experimental":[114],"results":[115],"show":[116],"that":[117],"proposed":[119],"can":[122],"capture":[123],"behaviors":[128],"achieve":[134],"decent":[135],"accuracy":[136],"(average":[137],"errors":[138],"3.85,":[140],"8.6,":[141],"8.82,":[142],"8.83":[144],"percent":[145],"20":[150],"four":[154],"modern":[155],"Nvidia":[156],"GPUs).":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}